marian-nmt/marian
1
1
Fork 0
mirror of https://github.com/marian-nmt/marian.git synced 2024-12-11 09:54:22 +03:00
Code Issues Packages Projects Releases Wiki Activity
Fast Neural Machine Translation in C++
12 Commits 41 Branches 10 Tags 44 MiB
C++ 85.4%
Cuda 8.3%
CMake 3.3%
Python 1.8%
Batchfile 0.4%
Other 0.7%
1505d3811f
Go to file
Marcin Junczys-Dowmunt 1505d3811f finished n-best lits
2016-04-14 21:27:15 +02:00
scripts turn into objects 2016-04-14 14:29:41 +02:00
src finished n-best lits 2016-04-14 21:27:15 +02:00
.gitignore first commit 2016-04-14 13:44:55 +02:00
CMakeLists.txt towards n-best-lists 2016-04-14 20:49:38 +02:00
LICENSE Initial commit 2016-04-14 11:27:41 +01:00
README note about vocabularies 2016-04-14 17:25:05 +02:00

README 

mkdir build
cd build
cmake ..
make -j

on Ubuntu 16.04, you need g++4.9 and cuda-7.5 and a boost version compiled with g++4.9

CUDA_BIN_PATH=/usr/local/cuda-7.5 BOOST_ROOT=/home/marcin/myboost cmake .. -DCMAKE_CXX_COMPILER=g++-4.9 -DCUDA_HOST_COMPILER=/usr/bin/g++-4.9

Vocabularies need to be converted to text with the scripts in the scripts folder. The end of sentence symbol is </s>. (Can be changed in decoder/search.h)